Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/nexus-substrate/nexus-agents/performance-optimizationnpx skills add nexus-substrate/nexus-agents --skill performance-optimizationgit clone --depth 1 https://github.com/nexus-substrate/nexus-agentsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00071 | $0.01334 |
| Opus 5 | $0.00036 | $0.00667 |
| Sonnet 5 | $0.00014 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
performance-optimization scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| **Synchronous I/O in hot path** | `readFileSync`, `execSync` per request | Async + worker pool, or cache the result | How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization Skill
When to apply
- Performance requirements are stated in the spec or issue (e.g., "list endpoint must p95 < 200ms")
- Users or monitoring report slow behavior with a reproducible scenario
- Core Web Vitals scores fall below "Good" thresholds (LCP < 2.5s, INP < 200ms, CLS < 0.1)
- A specific commit or PR introduced a measurable regression vs prior baseline
- Code handles datasets large enough that complexity dominates (n > 10k or rps > 100)
Skip when:
- There's no measurement showing a problem — "feels slow" without a profile is not a justification
- The fix would add complexity disproportionate to the win (5% improvement at the cost of unreadable code)
- Performance is dominated by a downstream system you don't control (e.g., the LLM round-trip)
- The hot path is run once per cold-start — micro-optimizing startup isn't worth the readability cost
"Premature optimization is the root of all evil." Don't optimize before you have evidence. The cost of complexity is permanent; the cost of waiting for evidence is one more profile run.
The MIFVG cycle
- MEASURE — establish baseline with real data. Synthetic benchmarks are starting points, not ground truth. Capture both p50 and p95.
- IDENTIFY — profile. Don't guess the bottleneck — measure it. Tools:
node --prof,clinic.js, browser DevTools Performance,pproffor memory. - FIX — address the specific bottleneck. One change at a time. If two things are slow, fix the worst one first and re-measure.
- VERIFY — re-measure with the same scenario. The improvement must be reproducible, not a single lucky run.
- GUARD — add a monitoring assertion, a test budget, or a performance gate so the fix doesn't silently regress. The Beyoncé Rule applies — if you measured it, put a guard on it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 88 lines · 71 tokens per session scan A ae7c6e92a55f
performance-optimization is a skill published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,334 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.